Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11076
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Cyprus"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cypriot" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Forever
    -0.75
     Tunnel
    -0.70
     bubble
    -0.69
     trailer
    -0.69
    Interstitial
    -0.68
    uberty
    -0.67
     tunnels
    -0.66
     tunnel
    -0.66
     elbow
    -0.63
    erella
    -0.62
    POSITIVE LOGITS
    pri
    3.69
    Pri
    1.95
     Ign
    1.15
     Pri
    1.13
     pri
    1.09
     Gregory
    1.04
    prus
    0.98
     Ath
    0.95
    Ign
    0.92
     priesthood
    0.90
    Activations Density 0.040%

    No Known Activations